© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26245
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acc
    -0.09
    archy
    -0.09
    eson
    -0.09
    Plane
    -0.09
    isd
    -0.08
     slam
    -0.08
    osas
    -0.08
     decades
    -0.08
    alf
    -0.08
    åł
    -0.08
    POSITIVE LOGITS
     CFR
    0.13
    %
    0.11
    °
    0.11
    .media
    0.11
    %-
    0.11
     perfectly
    0.10
     percent
    0.10
     yaÅŁ
    0.10
     Jah
    0.09
     ideally
    0.09
    Activations Density 0.556%

    No Known Activations